PaperHub

Kai-Wei Chang

~Kai-Wei_Chang1

28
论文总数
14.0
年均投稿
6.2
平均评分
接收情况23/28
会议分布
ICLR
14
NeurIPS
7
COLM
4
ICML
3

发表论文 (28 篇)

202521 篇

6.0
4

Controllable Generation via Locally Constrained Resampling

ICLR 2025Poster
6.0
5

Contradiction Retrieval via Contrastive Learning with Sparsity

ICML 2025Poster
5.8
4

Contradiction Retrieval Via Sparse-Aware Sentence Embedding

ICLR 2025Rejected
7.5
4

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

ICLR 2025Spotlight
-

Unlearning as Multi-Task Optimization: a normalized gradient difference approach with adaptive learning rate

ICLR 2025withdrawn
6.3
4

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

ICLR 2025Poster
6.7
3

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

COLM 2025Poster
7.3
4

Agree to Disagree? A Meta-Evaluation of LLM Misgendering

COLM 2025Poster
6.4
3

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

NeurIPS 2025Poster
6.3
4

Customize Multi-modal RAI Guardrails with Precedent-based predictions

COLM 2025Poster
5.6
5

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

ICLR 2025Poster
5.5
3

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

ICML 2025Poster
4.8
4

Q* Agent: Optimizing Language Agents with Q-Guided Exploration

ICLR 2025Rejected
7.8
4

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

NeurIPS 2025Spotlight
6.6
4

Contrastive Visual Data Augmentation

ICML 2025Poster
6.0
4

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

COLM 2025Poster
6.3
4

VideoPhy: Evaluating Physical Commonsense for Video Generation

ICLR 2025Poster
6.8
4

LaViDa: A Large Diffusion Model for Vision-Language Understanding

NeurIPS 2025Spotlight
6.8
4

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

NeurIPS 2025Poster
6.0
4

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

ICLR 2025Spotlight
5.2
5

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

ICLR 2025Poster
合作者 (20)